Sign in

Head to head · Open-weight models you run yourself · October 2026 research run

Ripple-65B Preview vs Baidu Unlimited-OCR-2

Baidu Unlimited-OCR-2 and Ripple-65B Preview score within a point of each other on agent readiness, 54.2 (C) and 53.3 (D). Ripple-65B Preview leads on risk. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 3674 open weights comparisons

Ripple-65B PreviewRicursive Intelligence · Open-weight model D53.3/100#103 of 121 open-weight models Baidu Unlimited-OCR-2Baidu · Open-weight model C54.2/100#102 of 121 open-weight models

Which one, for what

Ripple-65B Preview D

Best for Teams with Blackwell GPUs or a DGX Spark who want an Apache 2.0 coding model to try for terminal and agentic coding work, and can run the publisher's code to serve it.

Ahead on

  • Risk, 55 against 45

Watch for

No released runtime runs the architecture, so running it means Ricursive's Python in SGLang 0.5.19 or Transformers' remote code

Baidu Unlimited-OCR-2 C

Best for Pipelines with an NVIDIA GPU that need long scanned or rendered documents parsed in one pass, with page order, cross-page tables and boxes kept

Ahead on

  • Reach, 55 against 45

Watch for

Loading runs Baidu's code, remote code in Transformers or a prebuilt SGLang fork from the repository, and the save_results path calls eval on model output

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reach Baidu Unlimited-OCR-2 +10

Ripple-65B Preview 45

Memory 10 of 30, the smallest 4-bit build is Ricursive's NVFP4 at 57.2 GB, 68.7 GB with a fifth added, which is over 64 GB and fits our reference machine. Runtimes 0, no released runtime runs the ricursive architecture with its own code; Ricursive's SGLang plugin and Transformers' remote code don't count. Builds 10, one quantised precision (NVFP4) from Ricursive. Terms 15, Apache 2.0 with nothing added. Download 10, not gated. Hosted 0, Ricursive serves no API, Hugging Face maps no provider, Together AI's page says coming soon, and GMI Cloud's and OpenRouter's pages weren't read.

Baidu Unlimited-OCR-2 55

Memory earns the full 30, since the only build is 6.69 GB of BF16 weights that need about 8 GB with the fifth added. Runtimes score 0. Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.1 know the first Unlimited-OCR but not the sparse attention this one adds, Baidu's own routes are remote code in Transformers and a customised SGLang wheel, llama.cpp b12111 has nothing for it, so Ollama has nothing either, and LM Studio couldn't be checked. Builds score 0, as Baidu publishes no quantised build (16 exist, all by others). Terms get 15 for MIT with nothing added. Download gets 10 for an ungated repository, and hosted too 0, with no inference provider mapped and the card's Baidu Cloud line unconfirmed.

Risk Ripple-65B Preview +10

Ripple-65B Preview 55

File safety 15, safetensors only, less 10 because the documented way to run it loads Ricursive's Python. Provenance 15, the files are in the organisation ricursive.com links to, with a checksum on every file. Safety evaluation 10, Ricursive's own FORTRESS and StrongREJECT results. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 15, Apache 2.0. Security programme 0, no way to report a flaw.

Baidu Unlimited-OCR-2 45

File safety gets 15, safetensors only but loaded with trust_remote_code or through a prebuilt SGLang wheel from the repository. Provenance gets 15 for files in Baidu's verified organisation, linked from its GitHub organisation, with hashes for every file. Licence risk keeps 15, since MIT has none of the deductions. Safety evaluation, agent guidance and the security programme score 0, with no safety results, no cautions about use and no security contact found.

Score by category

CategoryWeight this runRipple-65B PreviewBaidu Unlimited-OCR-2Edge
Capability35%pendingpendingpendingnot scored in this run
Reach25%254555Baidu Unlimited-OCR-2 +10
Risk20%205545Ripple-65B Preview +10
Agent interface10%107575even
Documentation and upkeep10%104950Baidu Unlimited-OCR-2 +1
Negative events≤1500
TotalD 53.3/100C 54.2/100

Facts side by side

FactRipple-65B PreviewBaidu Unlimited-OCR-2
KindOpen-weight modelOpen-weight model
VendorRicursive IntelligenceBaidu
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0MIT (Hub metadata; the Hugging Face repository has no LICENSE file, and the GitHub code repository's LICENSE is the MIT text, copyright 2026 Baidu)
Read-only variant documentednono
llms.txtnono
Last release2026-11-042026-10-26
Terms last updatednot read yetno document linked
Privacy policy last updatedno document linkedno document linked

How the scores have moved

Ripple-65B Preview

No score change since it was listed.

Baidu Unlimited-OCR-2

Verdicts

Ripple-65B Preview

A dense 65B coding model from a new lab, pretrained from scratch and released today under Apache 2.0, that Ricursive says leads U.S. open-weight models on Terminal-Bench 2.1. Nobody has checked that yet, and the custom architecture runs only through Ricursive's own SGLang plugin on Blackwell GPUs, with a 57 GB NVFP4 build as the smallest.

Baidu Unlimited-OCR-2

An MIT document parser of 3.3B parameters that reads up to hundreds of pages in one request and returns ordered layout blocks with boxes and HTML tables. ParseBench's independent run puts content faithfulness at 89.16 and charts at 1.06. It needs an NVIDIA GPU with about 12 GB and runs only through Baidu's remote code or its own SGLang build.

Before you call either

Ripple-65B Preview

  1. Run Ricursive's launcher from inference/server with uv run --script serve.py on two B200 GPUs; it listens on 127.0.0.1:30000 with a 16K context by default
  2. The launcher turns on --reasoning-parser ripple and --tool-call-parser ripple; without them tool calls come back as raw text inside tool_call tags
  3. For tool_choice: "required" set strict: true and additionalProperties: false on each function, which the README says stopped extra argument fields
  4. Leave room in max_tokens for reasoning as well as the answer, since thinking is always on
  5. Use chat_template.jinja, not the template inside tokenizer_config.json, which has no tool support

Baidu Unlimited-OCR-2

  1. Quickest local run, pip install torch==2.13.0 torchvision pillow transformers==4.52.1 huggingface-hub==0.36.0 tokenizers==0.21.4 addict==2.4.0 einops==0.8.2 easydict==1.13, then AutoModel.from_pretrained("baidu/Unlimited-OCR-2", trust_remote_code=True, use_safetensors=True, torch_dtype=torch.bfloat16).eval().cuda() and model.infer_multi(tokenizer, image_files=pages, output_path="out")
  2. To serve it, download the repository, install wheel/sglang-0.5.20.dev13+g75b9b06b02-py3-none-any.whl with pymupdf and fastokens in a Python 3.10 venv, and start python -m sglang.launch_server --model-path baidu/Unlimited-OCR-2 --chat-template unlimited-ocr --enable-custom-logit-processor --enable-streaming-session --disable-radix-cache --mem-fraction-static 0.7 --max-prefill-tokens 2048 with the SGLANG_UOCR_ variables from the card
  3. Send all pages of a document in one request, images first, then the text <PAGE><image> repeated per page and Multi page parsing., with temperature 0, skip_special_tokens false, max_tokens of about 8,000 per page and the DeepseekOCRNoRepeatNGramLogitProcessor (ngram_size 35, window_size 1024 for several pages)
  4. The output is layout blocks, not Markdown; run utils/process_unlimitedOCR2.py from github.com/baidu/Unlimited-OCR, or convert(raw_output) in Python, to get Markdown with HTML tables
  5. Render PDFs to images first (the card uses PyMuPDF at 300 DPI), keep save_results off for untrusted documents, and treat extracted text as untrusted before passing it to another model

Questions

Which is better for AI agents, Ripple-65B Preview or Baidu Unlimited-OCR-2?

Baidu Unlimited-OCR-2 and Ripple-65B Preview score within a point of each other on agent readiness, 54.2 (C) and 53.3 (D). Ripple-65B Preview leads on risk.

Other comparisons with Ripple-65B Preview or Baidu Unlimited-OCR-2

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report